From: Robin Murphy <robin.murphy@arm.com> To: joro@8bytes.org, will@kernel.org Cc: iommu@lists.linux-foundation.org, yf.wang@mediatek.com, miles.chen@mediatek.com, wsd_upstream@mediatek.com, linux-kernel@vger.kernel.org Subject: [PATCH] iommu/iova: Improve 32-bit free space estimate Date: Thu, 3 Mar 2022 14:40:08 +0000 [thread overview] Message-ID: <033815732d83ca73b13c11485ac39336f15c3b40.1646318408.git.robin.murphy@arm.com> (raw) For various reasons based on the allocator behaviour and typical use-cases at the time, when the max32_alloc_size optimisation was introduced it seemed reasonable to couple the reset of the tracked size to the update of cached32_node upon freeing a relevant IOVA. However, since subsequent optimisations focused on helping genuine 32-bit devices make best use of even more limited address spaces, it is now a lot more likely for cached32_node to be anywhere in a "full" 32-bit address space, and as such more likely for space to become available from IOVAs below that node being freed. At this point, the short-cut in __cached_rbnode_delete_update() really doesn't hold up any more, and we need to fix the logic to reliably provide the expected behaviour. We still want cached32_node to only move upwards, but we should reset the allocation size if *any* 32-bit space has become available. Reported-by: Yunfei Wang <yf.wang@mediatek.com> Signed-off-by: Robin Murphy <robin.murphy@arm.com> --- drivers/iommu/iova.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index b28c9435b898..170e0f33040e 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -95,10 +95,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) cached_iova = to_iova(iovad->cached32_node); if (free == cached_iova || (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo)) { + free->pfn_lo >= cached_iova->pfn_lo)) iovad->cached32_node = rb_next(&free->node); + + if (free->pfn_lo < iovad->dma_32bit_pfn) iovad->max32_alloc_size = iovad->dma_32bit_pfn; - } cached_iova = to_iova(iovad->cached_node); if (free->pfn_lo >= cached_iova->pfn_lo) -- 2.28.0.dirty
WARNING: multiple messages have this Message-ID (diff)
From: Robin Murphy <robin.murphy@arm.com> To: joro@8bytes.org, will@kernel.org Cc: miles.chen@mediatek.com, iommu@lists.linux-foundation.org, yf.wang@mediatek.com, wsd_upstream@mediatek.com, linux-kernel@vger.kernel.org Subject: [PATCH] iommu/iova: Improve 32-bit free space estimate Date: Thu, 3 Mar 2022 14:40:08 +0000 [thread overview] Message-ID: <033815732d83ca73b13c11485ac39336f15c3b40.1646318408.git.robin.murphy@arm.com> (raw) For various reasons based on the allocator behaviour and typical use-cases at the time, when the max32_alloc_size optimisation was introduced it seemed reasonable to couple the reset of the tracked size to the update of cached32_node upon freeing a relevant IOVA. However, since subsequent optimisations focused on helping genuine 32-bit devices make best use of even more limited address spaces, it is now a lot more likely for cached32_node to be anywhere in a "full" 32-bit address space, and as such more likely for space to become available from IOVAs below that node being freed. At this point, the short-cut in __cached_rbnode_delete_update() really doesn't hold up any more, and we need to fix the logic to reliably provide the expected behaviour. We still want cached32_node to only move upwards, but we should reset the allocation size if *any* 32-bit space has become available. Reported-by: Yunfei Wang <yf.wang@mediatek.com> Signed-off-by: Robin Murphy <robin.murphy@arm.com> --- drivers/iommu/iova.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index b28c9435b898..170e0f33040e 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -95,10 +95,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free) cached_iova = to_iova(iovad->cached32_node); if (free == cached_iova || (free->pfn_hi < iovad->dma_32bit_pfn && - free->pfn_lo >= cached_iova->pfn_lo)) { + free->pfn_lo >= cached_iova->pfn_lo)) iovad->cached32_node = rb_next(&free->node); + + if (free->pfn_lo < iovad->dma_32bit_pfn) iovad->max32_alloc_size = iovad->dma_32bit_pfn; - } cached_iova = to_iova(iovad->cached_node); if (free->pfn_lo >= cached_iova->pfn_lo) -- 2.28.0.dirty _______________________________________________ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
next reply other threads:[~2022-03-03 14:40 UTC|newest] Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-03-03 14:40 Robin Murphy [this message] 2022-03-03 14:40 ` [PATCH] iommu/iova: Improve 32-bit free space estimate Robin Murphy 2022-03-03 23:08 ` Miles Chen 2022-03-03 23:08 ` Miles Chen via iommu 2022-03-03 23:36 ` Miles Chen 2022-03-03 23:36 ` Miles Chen via iommu 2022-03-04 9:41 ` Joerg Roedel 2022-03-04 9:41 ` Joerg Roedel 2022-03-04 11:32 ` Robin Murphy 2022-03-04 11:32 ` Robin Murphy 2022-03-05 0:03 ` Miles Chen 2022-03-05 0:03 ` Miles Chen via iommu
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=033815732d83ca73b13c11485ac39336f15c3b40.1646318408.git.robin.murphy@arm.com \ --to=robin.murphy@arm.com \ --cc=iommu@lists.linux-foundation.org \ --cc=joro@8bytes.org \ --cc=linux-kernel@vger.kernel.org \ --cc=miles.chen@mediatek.com \ --cc=will@kernel.org \ --cc=wsd_upstream@mediatek.com \ --cc=yf.wang@mediatek.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.